ファジー推論による母音認識と韓国語連続音声への応用

DOI Web Site Web Site

書誌事項

タイトル別名
  • A Vowel Recognition by Fuzzy Inference and Application to Recogniton of Continuous Korean Speech
  • ファジー スイロン ニ ヨル ボイン ニンシキ ト カンコクゴ レンゾク オン

この論文をさがす

抄録

In this paper, a new matching method by fuzzy inference is proposed. In vowel, variations of the formant frequencies depend on speakers and spoken situation. It is difficult to decide a prior value of width of the variations, so we represent their variations as fuzziness and make fuzzy rules. For consonant recognition, it is difficult to extract feature parameters. Therefore, here we use characteristics about configuration of autocorrelation function, power, zero crossing rates, and logarithmic energies.<br>As a result of experiment on the recognition of continuous Korean speech, it is shown that the fuzzy inference is effective to speech recognition of unspecified persons.

収録刊行物

キーワード

詳細情報 詳細情報について

問題の指摘

ページトップへ